Transparency signal for adopters, based on public metrics — NOT a quality score:
• Adoption: 7.7k GitHub stars (public metric)
• Maintenance: last push ~3 months ago (active)
• Openness: weights + inference code public (Apache-2.0)
• Docs: Paddle ERNIEKit, FastDeploy, HF/GitCode
Most of this number is GitHub stars. See /methodology/#scoring.
⚠️ Red Flags & Trade-offs (AMI)
- The headline open variant is 47B/3B MoE; the 0.3B dense is tiny but the flagship still needs real GPUs — verify which build you deploy. [ERNIE repo]
- Docs and ecosystem lean Chinese (PaddlePaddle / GitCode); English resources are thinner than Qwen or DeepSeek. [GitHub]
- Most reported benchmarks are Baidu's own; independent third-party testing is still limited. [ERNIE repo]
Each flag links to its primary source. See our Correction Policy.
📝 Report a correction or complaint
Corrections and complaints go straight to our editorial queue — read and actioned by the site operator, not lost in an inbox. No email needed.
Baidu's open-source ERNIE 4.5 family — 10 models (47B/3B MoE + 0.3B dense, Apache-2.0) — the framework+model 'double open' release of Jun 2025.
7.7k stars · 1.4k forks · last push Jul 2026
💡 Lighter Alternatives (If this is too heavy)
Disclaimer
Red Flags and the AMI score are editorial analysis, not endorsements. They are produced with AI assistance and reviewed by a human, but are not a substitute for reading the primary source. The Adoption & Maintainability Index (AMI) reflects public adoption and availability signals only — never a verdict on the science, the code quality, or the people behind a project. We are not affiliated with any lab, university, or company named on this page, and links point only at primary sources (papers, repositories, journals). Content is informational and not engineering, business, or investment advice.